© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50729
    Prev
    Next
    INDEX
    Explanations

    Antiviral treatments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    弟
    -0.09
     utf
    -0.08
     southern
    -0.08
    _utf
    -0.08
     Southern
    -0.08
     Yi
    -0.08
     Asia
    -0.08
     brown
    -0.08
    ysł
    -0.08
     Xiao
    -0.08
    POSITIVE LOGITS
     bal
    0.11
    Rem
    0.10
     рем
    0.09
     fav
    0.09
     rem
    0.09
    .Rem
    0.09
    Bal
    0.09
     pax
    0.09
     Rem
    0.09
    (rem
    0.09
    Activations Density 0.001%

    No Known Activations